| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LIBERO | Being-H0.7 | Success Rate99.2 | 17 | 1mo ago | |
| Real-World Tabletop | STEREOPOLICY-DP | BANANA PNP Success Rate16 | 7 | 22d ago | |
| PH Toolhang (test) | Success Rate86 | 6 | 3mo ago | ||
| PH Square (test) | Success Rate94 | 6 | 3mo ago | ||
| PH Lift (test) | Success Rate100 | 6 | 3mo ago | ||
| PH Can (test) | Success Rate98 | 6 | 3mo ago | ||
| Real-World Tabletop Manipulation OOD-B (Out-of-Distribution Backgrounds) | AC-LAM | Success Rate33.3 | 5 | 1mo ago | |
| Real-World Tabletop Manipulation Out-of-Distribution Distractors | AC-LAM | Success Rate53.3 | 5 | 1mo ago | |
| Real-World Tabletop Manipulation (In-Distribution) | AC-LAM | Success Rate60 | 5 | 1mo ago | |
| IsaacSim benchmark | OPTKPSolver | Run Success Rate100 | 4 | 15d ago | |
| Real-world tabletop manipulation tasks v1.0 (test) | Pick Up Banana Success Rate80 | 3 | 14d ago | ||
| ALLEX humanoid (seen unseen tasks) | RoboCurate | Success Rate (P&P Can, In-distribution)47.9 | 3 | 3mo ago |
